1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
"""
scrapy.linkextractors
This package contains a collection of Link Extractors.
For more info see docs/topics/link-extractors.rst
"""
from __future__ import annotations
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from collections.abc import Iterable
from re import Pattern
# common file extensions that are not followed if they occur in links
IGNORED_EXTENSIONS = [
# archives
"7z",
"7zip",
"bz2",
"rar",
"tar",
"tar.gz",
"xz",
"zip",
# images
"mng",
"pct",
"bmp",
"gif",
"jpg",
"jpeg",
"png",
"pst",
"psp",
"tif",
"tiff",
"ai",
"drw",
"dxf",
"eps",
"ps",
"svg",
"cdr",
"ico",
"webp",
# audio
"mp3",
"wma",
"ogg",
"wav",
"ra",
"aac",
"mid",
"au",
"aiff",
# video
"3gp",
"asf",
"asx",
"avi",
"mov",
"mp4",
"mpg",
"qt",
"rm",
"swf",
"wmv",
"m4a",
"m4v",
"flv",
"webm",
# office suites
"xls",
"xlsm",
"xlsx",
"xltm",
"xltx",
"potm",
"potx",
"ppt",
"pptm",
"pptx",
"pps",
"doc",
"docb",
"docm",
"docx",
"dotm",
"dotx",
"odt",
"ods",
"odg",
"odp",
# other
"css",
"pdf",
"exe",
"bin",
"rss",
"dmg",
"iso",
"apk",
"jar",
"sh",
"rb",
"js",
"hta",
"bat",
"cpl",
"msi",
"msp",
"py",
]
def _matches(url: str, regexs: Iterable[Pattern[str]]) -> bool:
return any(r.search(url) for r in regexs)
def _is_valid_url(url: str) -> bool:
return url.split("://", 1)[0] in {"http", "https", "file", "ftp"}
# Top-level imports
from scrapy.linkextractors.lxmlhtml import LxmlLinkExtractor as LinkExtractor
__all__ = [
"IGNORED_EXTENSIONS",
"LinkExtractor",
]
|
